Dawnn benchmarking dataset: Organoid processing and label simulation

This project is a collection of files to allow users to reproduce the model development and benchmarking in "Dawnn: single-cell differential abundance with neural networks" (Hall and Castellano, under review). Dawnn is a tool for detecting differential abundance in single-cell RNAseq datasets. It is available as an R package here. Please contact us if you are unable to reproduce any of the analysis in our paper.
The files in this collection correspond to the benchmarking dataset based on single-cell RNAseq of bile duct organoids.

FILES:
Input datasets
Dataset from "Cholangiocyte organoids can repair bile ducts after transplantation in the human liver". Science 371(6531) pp. 839-846 (2021).

E-MTAB-8495.aggregated_filtered_normalised_counts.mtx Single-cell RNAseq expresison matrix.
E-MTAB-8495.aggregated_filtered_normalised_counts.mtx_cols Column names.
E-MTAB-8495.aggregated_filtered_normalised_counts.mtx_rows Row names.

Data processing code

process_organoid_cells_data.R Generates benchmarking dataset from input data. (Reads E-MTAB-8495.aggregated_filtered_normalised_counts.* files; Runs the standard Seurat pipeline; Saves the resulting Seurat dataset as organoid_cells.RDS)
simulate_organoid_labels_Rscript.R R code to simulate labels for benchmarking.
simulate_organoid_labels_bash.sh Bash script to execute simulate_organoid_labels_Rscript.R. Outputs stored in benchmark_dataset_organoid_labels.csv.

Resulting datasets

organoid_cells.RDS Seurat dataset generated by process_organoid_cells_data.R.
benchmark_dataset_organoid_labels.csv Cell labels generated by simulate_organoid_labels_bash.sh.

本项研究汇集了一系列文件，旨在使用户能够重现《Dawnn：基于神经网络的单个细胞差异丰度检测》（Hall 和 Castellano，待审稿）中的模型开发与基准测试。Dawnn 是一款针对单个细胞 RNA 测序数据集进行差异丰度检测的工具，现以 R 软件包的形式提供。若您在重现本文中的任何分析时遇到困难，请与我们联系。本集合中的文件对应于基于单个细胞 RNA 测序胆管类器官的基准测试数据集。

文件列表：

输入数据集

来自《胆管类器官在人类肝脏移植后可修复胆管》（Science 371(6531) pp. 839-846, 2021）的数据集。

E-MTAB-8495.aggregated_filtered_normalised_counts.mtx 单个细胞 RNA 测序表达矩阵。
E-MTAB-8495.aggregated_filtered_normalised_counts.mtx_cols 列名。
E-MTAB-8495.aggregated_filtered_normalised_counts.mtx_rows 行名。

数据处理代码

process_organoid_cells_data.R 生成基准测试数据集的 R 代码。 （读取 E-MTAB-8495.aggregated_filtered_normalised_counts.* 文件；运行标准的 Seurat 工作流程；将生成的 Seurat 数据集保存为 organoid_cells.RDS）
simulate_organoid_labels_Rscript.R 用于模拟基准测试标签的 R 代码。
simulate_organoid_labels_bash.sh 执行 simulate_organoid_labels_Rscript.R 的 Bash 脚本。输出存储在 benchmark_dataset_organoid_labels.csv 中。

结果数据集

organoid_cells.RDS 由 process_organoid_cells_data.R 生成的 Seurat 数据集。
benchmark_dataset_organoid_labels.csv 由 simulate_organoid_labels_bash.sh 生成的细胞标签。